Captured motion data is widely used in virtual human motion control and synthesis. Usually, the motion data has a native skeleton definition. To apply captured motion on virtual human skin model, the model should have an underlying skeleton that matches the one defined by the motion data. This paper proposes an algorithm called LMSA (lazy match based on semantic analysis) which generates skeleton for existing human model and matches it to the motion data when the motion data is loaded. The LMSA algorithm first generates Candidate-Joint-Set for a human model with a group of parallel planes and then applies the same semantic analysis to both the Candidate-Joint-Set and the skeleton of motion data to match them. By using LMSA algorithm, different motion data can be applied to the existing human model directly without predefining skeleton for human model.